Vehicle torque control method and device, vehicle and storage medium

Abstract

Embodiments of the present application relate to a vehicle torque control method and device, a vehicle and a storage medium. In the vehicle driving process, the vehicle speed signal and the gear signal are obtained; the video information of the target area around the vehicle is obtained according to the gear signal; whether the video information identifies the existence of the bumpy road condition in the video picture is determined; in the case that the bumpy road condition exists in the video picture, the bumpy road condition meets the preset position condition, and the vehicle speed signal meets the preset vehicle speed condition, the tooth engagement torque is applied to the motor of the vehicle. Thus, the tooth engagement torque can be applied when the vehicle approaches the speed bump or the pothole road, the continuous torque application is avoided, the vehicle endurance is improved, the road condition and the vehicle state are identified, the torque is dynamically adjusted, and the control precision and comfort are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method, device, vehicle, and storage medium for controlling vehicle torque. Background Technology

[0002] When the recycling intensity of a new energy vehicle is zero and the driver has no torque demand, the vehicle is in a free-gliding state, and the electric drive gears rotate freely only by inertia. When the vehicle passes over speed bumps or potholes under this condition, the road impact will cause the driving gear and the driven gear to collide momentarily, resulting in knocking impact and abnormal noise.

[0003] Existing technologies typically reduce tooth knocking during free gliding by continuously applying a tooth torque to keep the gears engaged. However, this approach requires the motor to output low torque for extended periods, leading to increased energy consumption. Furthermore, it cannot dynamically adjust to varying bump intensities or road conditions, resulting in insufficient control precision.

[0004] Therefore, how to intelligently adjust the gear torque according to real-time road conditions and vehicle status while avoiding gear knocking and abnormal noise has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, in order to solve the above-mentioned technical problems or some of the technical problems, the present invention provides a method, device, vehicle and storage medium for controlling vehicle torque.

[0006] In a first aspect, embodiments of the present invention provide a method for controlling vehicle torque, comprising:

[0007] During the vehicle's operation, the vehicle's speed signal and gear signal are acquired.

[0008] Video information of the target area around the vehicle is obtained based on the gear position signal;

[0009] The video information is used to identify whether there are bumpy road conditions in the video footage;

[0010] If the bumpy road conditions are present in the video footage, and the bumpy road conditions meet preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, then a toothed torque is applied to the motor of the vehicle.

[0011] In one possible implementation, acquiring video information of the target area around the vehicle based on the gear position signal includes:

[0012] When the gear position signal indicates that the vehicle is currently in drive, the forward-facing camera in front of the vehicle is controlled to acquire video information of a first target area on the road in front of the vehicle;

[0013] When the gear position signal indicates that the vehicle is currently in reverse gear, the rear-view camera behind the vehicle is controlled to acquire video information of a second target area on the road behind the vehicle.

[0014] When the gear position signal indicates that the vehicle is currently in neutral or park, the front-view camera and the rear-view camera are put into standby mode.

[0015] In one possible implementation, the method further includes:

[0016] The lateral and longitudinal ranges of the first target area are adjusted according to the vehicle speed when the vehicle is in forward gear, and the lateral and longitudinal ranges of the second target area are adjusted according to the vehicle speed when the vehicle is in reverse gear, wherein the lateral and longitudinal ranges are positively correlated with the vehicle speed.

[0017] In one possible implementation, when the bumpy road condition exists in the video footage, and the bumpy road condition meets preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, applying a gear torque to the vehicle's motor includes:

[0018] When the energy recovery intensity of the vehicle is zero and the driver's required wheel-side torque signal value is zero, determine whether the longitudinal distance between the bumpy road condition in the video and the center of gravity of the vehicle is less than a preset distance, and determine whether the lateral distance between the bumpy road condition and the center of gravity of the vehicle is less than half the width of the vehicle.

[0019] If the longitudinal distance is less than a preset distance and the lateral distance is less than half the width of the vehicle, the bumpy road condition is determined to meet the preset position condition. If the vehicle speed signal indicates that the vehicle speed is less than the preset vehicle speed, the vehicle speed signal is determined to meet the preset vehicle speed condition, and a toothed torque is applied to the motor of the vehicle.

[0020] In one possible implementation, the method further includes:

[0021] When the longitudinal distance is greater than or equal to a preset distance, the unloading torque of the motor of the vehicle is applied.

[0022] Alternatively, if the lateral distance is greater than or equal to half the width of the vehicle, the motor of the vehicle is unloaded with a toothed torque.

[0023] Alternatively, if the vehicle speed signal indicates that the vehicle speed is greater than or equal to the preset vehicle speed, the motor of the vehicle is unloaded with a gear torque.

[0024] Alternatively, if the bumpy road conditions are not present in the video footage, the motor unloads the gear torque for the vehicle.

[0025] In one possible implementation, applying a gear torque to the vehicle's motor includes:

[0026] Identify the type of road condition described in the bumpy road condition;

[0027] When the road condition type is a speed bump, the target torque value is determined based on the height and / or width of the speed bump, and the target torque value is positively correlated with the height and / or width of the speed bump;

[0028] When the road condition is a pothole, the target torque value is determined based on the depth and / or area of ​​the pothole, and the target torque value is positively correlated with the depth and / or area of ​​the pothole.

[0029] Apply gear torque to the vehicle's motor according to the target torque value.

[0030] In one possible implementation, the method further includes:

[0031] Acquire vehicle driving data, historical torque application data, historical bumpy road condition information, and noise information when the vehicle driver passes through bumpy road conditions during a historical time period;

[0032] The vehicle driving data, the historical torque application data, the historical bumpy road condition information, and the noise information are used as model training data to train the target model so that the trained target model outputs a torque correction coefficient.

[0033] When the video footage shows the bumpy road conditions, the trained target model outputs the torque correction coefficient of the current vehicle, so as to correct the target torque value according to the torque correction coefficient.

[0034] The vehicle's motor is subjected to a gear torque based on the corrected target torque value.

[0035] Secondly, embodiments of the present invention provide a vehicle torque control device, comprising:

[0036] The first acquisition module is used to acquire the vehicle speed signal and gear signal of the vehicle during the vehicle's operation.

[0037] The second acquisition module is used to acquire video information of the target area around the vehicle based on the gear signal;

[0038] The identification module is used to identify whether there are bumpy road conditions in the video footage based on the video information;

[0039] The control module is used to apply a toothed torque to the motor of the vehicle when the bumpy road condition exists in the video frame, the bumpy road condition meets a preset position condition, and the vehicle speed signal meets a preset vehicle speed condition.

[0040] Thirdly, embodiments of the present invention provide a vehicle, including: a processor and a memory, wherein the processor is configured to execute a vehicle torque control program stored in the memory to implement the vehicle torque control method described in any one of the first aspects above.

[0041] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the vehicle torque control method described in any of the first aspects above.

[0042] The vehicle torque control scheme provided in this invention acquires vehicle speed and gear signals during vehicle operation; obtains video information of the target area surrounding the vehicle based on the gear signals; identifies whether bumpy road conditions exist in the video footage; and applies gear-driven torque to the vehicle's motor when bumpy road conditions are present in the video footage and meet preset position and speed conditions. This allows for the application of gear-driven torque when the vehicle approaches speed bumps or potholes, avoiding continuous torque application, improving vehicle range, and dynamically adjusting torque based on road conditions and vehicle status, thereby enhancing control precision and comfort. Attached Figure Description

[0043] Figure 1 A schematic flowchart illustrating a vehicle torque control method provided in an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of the structure of a vehicle torque control device provided in an embodiment of the present invention;

[0045] Figure 3 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] To facilitate understanding of the embodiments of the present invention, further explanations and descriptions will be provided below with reference to the accompanying drawings and specific embodiments. These embodiments do not constitute a limitation on the embodiments of the present invention.

[0048] Figure 1 This is a flowchart illustrating a vehicle torque control method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method specifically includes:

[0049] S11. During vehicle operation, acquire vehicle speed and gear signals.

[0050] The vehicle torque control method provided in this invention is applied to a vehicle, which can be a new energy vehicle. It is suitable for the operating conditions of new energy vehicles in daily road driving, especially when the vehicle passes through speed bumps, potholes or other bumpy road surfaces. By dynamically applying gear torque, it suppresses gear knocking and abnormal noise, improves driving comfort, and reduces energy consumption. It is suitable for urban roads, highways and various uneven road surface driving scenarios.

[0051] In this embodiment, during vehicle operation, vehicle speed and gear position signals are read in real time via a vehicle bus (e.g., CAN bus). The vehicle speed signal reflects the instantaneous speed of the vehicle, and the gear position signal determines the current driving state, which may include: drive (D), reverse (R), neutral (N), parking (P), etc. These signals are input to the control unit to determine whether the vehicle is in a free-coasting state and serve as triggering conditions or control parameters for subsequent gear torque application strategies.

[0052] Specifically, the vehicle speed signal can be provided by a vehicle speed sensor or wheel speed sensor, acquiring front or rear wheel speed data. This data is then fused by the vehicle control unit (VCU) to output the overall vehicle speed, or the currently displayed vehicle speed can be directly read as the vehicle speed signal. The gear position signal can be provided by the transmission or electric drive controller. The acquired vehicle speed signal undergoes filtering to remove sensor noise and transient pulse interference. The gear position signal is also de-jittered to ensure that incorrect judgments are not triggered during rapid shifts or malfunctions. Simultaneously, the vehicle speed signal and gear position signal timestamps can be synchronized to form a unified real-time status data frame.

[0053] In one possible implementation, the control unit determines whether the vehicle meets the free-coasting conditions based on the collected signals: the vehicle speed is greater than zero and less than a preset threshold (e.g., 0–150 km / h), the gear is in D or R, the driver has not requested wheel torque (wheel torque demand signal is 0), and the energy recovery intensity is 0. When the free-coasting conditions are met, the control unit uses the vehicle speed signal and gear signal as triggering conditions and reference parameters for the subsequent gear torque application strategy, determining whether to apply or unload gear torque, and dynamically adjusting the torque amplitude and application timing.

[0054] S12. Obtain video information of the target area around the vehicle based on the gear position signal.

[0055] In this embodiment, the area in front of or behind the vehicle is determined based on the current vehicle gear signal: when in forward gear, the area in front of the vehicle is the target area, and video information from the forward-facing camera is prioritized. When in reverse gear, the area behind the vehicle is the target area, and video information from the rear-facing camera is prioritized. The actual detection areas in the longitudinal and lateral directions can be calculated based on the vehicle width, camera installation position, and field of view. For example, the longitudinal area can cover 0–30 meters extending longitudinally from the front of the vehicle, and the lateral area can cover half the width of the vehicle.

[0056] In one possible implementation, at the moment of gear shifting (within five seconds before and after the shift), the preceding and following videos can be captured simultaneously. Short-term buffering and confidence assessment are used to determine the video source of the final target area, thus avoiding blind spots.

[0057] The video signal output by the camera is transmitted to the control unit through the interface, and the video data is synchronized with the gear signal to form a continuous frame sequence with timestamps for subsequent target detection and speed bump / pothole recognition processing.

[0058] In one possible implementation, when the gear signal indicates that the vehicle is currently in drive, the front-view camera is controlled to acquire video information of a first target area on the road in front of the vehicle; when the gear signal indicates that the vehicle is currently in reverse, the rear-view camera is controlled to acquire video information of a second target area on the road behind the vehicle; when the gear signal indicates that the vehicle is currently in neutral or park, the front-view camera and the rear-view camera are controlled to standby.

[0059] In this embodiment, when the gear signal indicates that the vehicle is in drive, the front-view camera is activated to capture video information of a first target area on the road ahead, used to identify speed bumps, potholes, and other obstacles. When the gear signal indicates that the vehicle is in reverse, the rear-view camera is activated to capture video information of a second target area on the road behind, used to identify speed bumps, potholes, and other obstacles along the vehicle's reversing path. When the gear signal indicates that the vehicle is in neutral or park, both the front-view and rear-view cameras enter standby mode and stop video capture to reduce power consumption and extend camera lifespan.

[0060] Optionally, the video can be cropped based on the first and second target regions defined by the gear position signal, processing only the key areas in front of or behind the vehicle (areas the vehicle will pass through), improving recognition efficiency. Brightness enhancement, noise reduction, or distortion correction can be applied to the cropped area to improve the accuracy of speed bump or pothole recognition. Specifically, the cropping range can be the 80% horizontal mid-area and the 60%-90% vertical lower-area, cropping out non-road redundant areas such as the sky and roadside vegetation to reduce the amount of data for subsequent processing. Then, the cropped image undergoes noise reduction, grayscale conversion, and contrast enhancement. Noise reduction uses a Gaussian filtering algorithm to remove random noise from the image; grayscale conversion uses a weighted average method to convert the color image to grayscale; and contrast enhancement uses histogram equalization to highlight the difference between road obstacles and the background.

[0061] In one possible implementation, the lateral and longitudinal ranges of a first target area are adjusted according to the vehicle speed when the vehicle is in forward gear, and the lateral and longitudinal ranges of a second target area are adjusted according to the vehicle speed when the vehicle is in reverse gear, wherein the lateral and longitudinal ranges are positively correlated with the vehicle speed.

[0062] In this embodiment, the longitudinal range of the first target area represents the longitudinal observation distance in front of the vehicle, and the lateral range represents the left and right observation width in front of the vehicle. These ranges can be dynamically adjusted according to the vehicle speed. The higher the speed, the larger the longitudinal and lateral ranges become to ensure that road obstacles can still be identified in advance at high speeds; conversely, the smaller the longitudinal and lateral ranges become at lower speeds to reduce redundant information processing. Specifically, the range of the captured video can be adjusted by changing the lens ratio of the camera or by activating a wide-angle lens.

[0063] The longitudinal range of the second target area represents the longitudinal observation distance behind the vehicle, and the lateral range represents the left and right observation width behind the vehicle. The longitudinal and lateral ranges of the second target area are also positively correlated with the vehicle speed. The higher the vehicle speed, the larger the lateral and longitudinal ranges; the lower the vehicle speed, the smaller the lateral and longitudinal ranges, in order to optimize camera processing efficiency and reduce power consumption.

[0064] A dynamic mapping relationship can be established between vehicle speed and target area range. Different vehicle speeds correspond to different longitudinal and lateral range values, which can be achieved using linear, nonlinear, or piecewise functions to meet the safety visibility requirements at different vehicle speeds.

[0065] In one possible implementation, the front-view or rear-view camera adjusts its pitch angle (vertical field of view) according to vehicle speed. The higher the speed, the greater the downward tilt of the pitch angle to expand the longitudinal observation distance of the road ahead; at lower speeds, the pitch angle is moderately reduced. The yaw angle (horizontal field of view) can be adjusted simultaneously, slightly expanding the left and right field of view as vehicle speed increases, ensuring the identification of speed bumps or obstacles at high speeds. The adjusted camera angle matches the target area dynamically determined based on vehicle speed, ensuring that the image includes the complete target area and improving the accuracy and real-time performance of speed bump, pothole, or obstacle identification.

[0066] S13. Identify whether there are bumpy road conditions in the video footage based on the video information.

[0067] In this embodiment, video frames of the target area are preprocessed, including but not limited to: grayscale conversion or contrast enhancement to improve the clarity of road surface features. Noise reduction processing, such as Gaussian filtering or median filtering, is performed to reduce interference from lighting variations, rain, or dust. Distortion correction can be performed to eliminate the effects of camera lens distortion. After preprocessing, road surface morphology features are extracted, including height differences, edge features, texture variations, and continuous uneven structures. Geometric models of typical bumpy road conditions such as speed bumps, potholes, and seams are pre-modeled, using features such as trapezoidal, arc-shaped, or wavy shapes. A classification model is trained based on the acquired features of different bumpy road conditions to identify bumpy road conditions in the video footage. Optical flow analysis, depth estimation, or stereo vision are combined to obtain information on the longitudinal height variation of the road surface.

[0068] The extracted features are compared with a preset bumpy road condition template or a trained classification model. When a height difference or continuous uneven features exceed a threshold, a bumpy road condition is determined to exist in the video footage. The system can output the bumpy road condition type (speed bump, pothole, seam, etc.), location coordinates (longitudinal and lateral), and size parameters (speed bump height and width, pothole depth and area, etc.) to provide a reference for subsequent tooth torque application. Alternatively, the similarity between the currently acquired bumpy road condition image and a preset bumpy road condition image can be calculated. When the similarity is greater than a preset value (e.g., 80%), the currently acquired bumpy road condition is identified as a preset bumpy road condition.

[0069] In one possible implementation, an improved YOLOv5 convolutional neural network model is used to extract edge, texture, and shape features from the preprocessed video image during feature extraction. To address the issue of insufficient accuracy in recognizing small potholes and low speed bumps, the model adds a small target detection layer to enhance its ability to capture features of small obstacles. The extracted features specifically include the strip-shaped protrusions of speed bumps and the concave contours of potholes.

[0070] The extracted features are input into a trained support vector machine (SVM) classification model to classify and identify road obstacles. The classification model is optimized through extensive sample training and can accurately distinguish speed bumps, potholes, and other road surface types, and mark the specific regions of obstacles in the image. During model training, road obstacle sample datasets under different lighting conditions (strong light, weak light, backlight) and different weather conditions (sunny day, rainy day, foggy day) are introduced to ensure high recognition accuracy even in complex environments.

[0071] S14. If there is a bumpy road condition in the video footage, and the bumpy road condition meets the preset position conditions and the vehicle speed signal meets the preset vehicle speed conditions, apply a toothed torque to the vehicle's motor.

[0072] In this embodiment, when a video image is detected by an image acquisition device such as a camera to include bumpy road conditions such as speed bumps and potholes, the position coordinates of the bumpy road conditions in the video image are obtained. Based on the camera's intrinsic calibration parameters (focal length, pixel size, etc.) and extrinsic installation position parameters (relative position of the camera to the vehicle's center of gravity, shooting angle, etc.), combined with the pixel coordinates of the bumpy road conditions in the video image, the two-dimensional image coordinates are converted into three-dimensional world coordinates through perspective transformation. Then, the longitudinal distance (distance along the vehicle's direction of travel) and lateral distance (distance perpendicular to the vehicle's direction of travel) between the bumpy road conditions and the vehicle's center of gravity are accurately calculated using triangulation.

[0073] When the vehicle is in a free-gliding state, the longitudinal and lateral distances of the bumpy road conditions are compared with preset thresholds. When the longitudinal distance between the bumpy obstacle and the vehicle's center of gravity is ≤30 meters (longitudinal preset threshold), and the lateral distance between the bumpy obstacle and the vehicle's center of gravity is ≤ half the width of the vehicle (the obstacle is determined to be on the vehicle's driving path), the bumpy road conditions are determined to meet the preset position conditions. If the current vehicle speed meets the preset speed conditions (for example, if the vehicle speed is less than the preset speed of 30 km / h, the preset speed conditions are determined to be met), a tooth-gripping torque is applied to the motor to keep the vehicle's active gear and passive gear in contact, preventing tooth knocking impact caused by bumps.

[0074] In one possible implementation, when the energy recovery intensity of the vehicle is zero and the driver's required wheel-side torque signal value is zero, it is determined whether the longitudinal distance between the bumpy road conditions in the video and the vehicle's center of gravity is less than a preset distance, and whether the lateral distance between the bumpy road conditions and the vehicle's center of gravity is less than half the width of the vehicle.

[0075] If the longitudinal distance is less than the preset distance and the lateral distance is less than half the width of the vehicle, the bumpy road condition is determined to meet the preset position condition. If the vehicle speed signal indicates that the vehicle speed is less than the preset vehicle speed, the vehicle speed signal is determined to meet the preset vehicle speed condition, and a toothed torque is applied to the vehicle's motor.

[0076] In this embodiment, the vehicle controller reads the energy recovery intensity signal output by the vehicle control system in real time, as well as the demand wheel-side torque signal obtained by converting the driver's accelerator pedal (or drive command). When the energy recovery intensity is detected to be zero and the demand wheel-side torque signal is zero, the controller determines that the vehicle is currently in a free-coasting condition.

[0077] The image recognition module performs ground calibration and target detection on the video footage currently captured by the camera, identifying the pixel coordinates of bumpy road conditions (including speed bumps, potholes, etc.) in the image. Combining the camera's installation calibration parameters (field of view, focal length, installation height, etc.) and vehicle pose data, the pixel coordinates are converted into real-world three-dimensional coordinates relative to the vehicle's center of mass using monocular depth estimation or structured optical flow methods, thereby obtaining the longitudinal and lateral distances of the bumpy road conditions.

[0078] If the longitudinal distance of the bumpy road condition is less than a preset distance (e.g., 30 meters), and the lateral distance of the bumpy road condition is less than half the width of the vehicle, the bumpy road condition is determined to meet the preset position conditions; otherwise, it is determined not to meet the conditions, and the process of applying the tooth torque is terminated.

[0079] Simultaneously, the controller reads the vehicle speed signal in real time and compares the current vehicle speed with a preset vehicle speed threshold (e.g., 30 km / h). When the vehicle speed is less than the preset vehicle speed threshold, the speed condition is determined to be met, and the gear torque is applied.

[0080] In one possible implementation, the toothed torque is unloaded from the vehicle motor when the longitudinal distance is greater than or equal to a preset distance; or, the toothed torque is unloaded from the vehicle motor when the lateral distance is greater than or equal to half the vehicle width; or, the toothed torque is unloaded from the vehicle motor when the vehicle speed signal indicates that the vehicle speed is greater than or equal to a preset vehicle speed; or, the toothed torque is unloaded from the vehicle motor when there are no bumpy road conditions in the video footage.

[0081] In this embodiment, during the application of the tooth-aligning torque, or when determining whether the tooth-aligning torque needs to be applied, the vehicle controller continuously monitors the location of the bumpy road conditions, vehicle speed signals, and video recognition results. If any of the application conditions are not met, the tooth-aligning torque is unloaded, or the tooth-aligning torque is not applied to the vehicle.

[0082] Specifically, the image recognition module updates the longitudinal distance of the bumpy road condition relative to the vehicle's center of gravity in real time. When the detected longitudinal distance is greater than or equal to a preset distance (e.g., 30 meters), the controller determines that the bumpy road condition is no longer within the vehicle's critical impact zone and immediately sends a torque release command to the drive motor to unload the gear torque. Alternatively, when the lateral distance of the bumpy road condition relative to the vehicle's center of gravity is greater than or equal to half the vehicle's width, the controller determines that the bumpy road condition is not within the vehicle's actual driving path and unloads the gear torque. Alternatively, the controller continuously reads the vehicle speed signal; when the vehicle speed signal indicates that the current vehicle speed is greater than or equal to a preset speed threshold (e.g., 30 km / h), it indicates that the vehicle is in a high-speed or medium-high-speed driving state, and the gear torque is unloaded. Alternatively, if the video image does not detect the bumpy road condition, the gear torque is unloaded.

[0083] As an example, the system collects vehicle speed signals, energy recovery intensity signals, driver-demanded wheel-side torque signals, gear position signals, and video signals from a camera. The video signals are processed to identify speed bumps or potholes and calculate their relative coordinates to the vehicle. When the energy recovery intensity is 0 and the driver-demanded wheel-side torque signal is 0, if a speed bump / pothole is detected in front of the vehicle in D gear or behind the vehicle in R gear, and the vehicle speed is less than or equal to 30 km / h, and the longitudinal distance between the speed bump / pothole and the vehicle's center of gravity is less than or equal to 30 meters, and the lateral distance is less than or equal to half the vehicle's width, a toothed torque is applied to the motor. If the vehicle speed is greater than 30 km / h, or no speed bump / pothole is detected, or the longitudinal distance between the speed bump / pothole and the vehicle's center of gravity is greater than 30 meters, or the lateral distance is greater than half the vehicle's width, the toothed torque needs to be unloaded from the motor. When applying or unloading gear torque, the torque needs to be filtered.

[0084] In one possible implementation, applying a gear torque to the vehicle's motor includes:

[0085] Identify the road condition type of bumpy road conditions; when the road condition type is speed bump, determine the target torque value based on the height and / or width of the speed bump, and the target torque value is positively correlated with the height and / or width of the speed bump; when the road condition type is pothole, determine the target torque value based on the depth and / or area of ​​the pothole, and the target torque value is positively correlated with the depth and / or area of ​​the pothole; apply gear torque to the vehicle's motor based on the target torque value.

[0086] In this embodiment, after identifying bumpy road conditions in the video footage, the vehicle control system performs type identification and parameter extraction on the bumpy road conditions to generate more accurate gear torque commands.

[0087] During road condition type identification, the image processing module uses road video captured by a camera to classify bumpy road conditions using a deep learning model (e.g., a semantic segmentation model), distinguishing them into speed bumps and potholes. (For example, if a bumpy road condition has regular lateral bulges and smooth edges, it is identified as a speed bump; if the bumpy area is pitted and has an irregular outline, it is identified as a pothole.) Alternatively, it performs similarity recognition; if the similarity to a preset speed bump image is greater than a set value (e.g., 80%), it is identified as a speed bump; otherwise, it is identified as a pothole.

[0088] When the road condition is identified as a speed bump, the image recognition module further extracts key structural parameters of the speed bump, including its height and / or width. The controller calculates the target torque value based on these parameters according to a preset mapping relationship: the higher the speed bump, the stronger the longitudinal impact on the vehicle, and the greater the required target torque; the wider the speed bump, the longer the impact duration, and the greater the required target torque. Therefore, the target torque value is positively correlated with the height and / or width of the speed bump.

[0089] When the road surface is uneven, the image recognition module extracts the depth information of the pothole area (using binocular vision, structured light, deep neural network estimation, etc.) and the area of ​​the pothole. The controller calculates the target gear torque to maintain gear engagement based on the depth and / or area: the deeper the pothole, the more pronounced the instantaneous tire sinking, and the greater the required shock-absorbing torque; the larger the pothole area, the longer the vehicle is subjected to the impact, and the greater the torque required. Therefore, the target torque value is positively correlated with the depth and / or area of ​​the pothole. The target torque value can be obtained by increasing a preset base torque value.

[0090] For example, the base torque value can be initially based on 3% to 5% of the motor's rated torque. When the identified obstacle is a speed bump, the base torque value is determined based on the height and width of the speed bump. For every 5mm increase in the height of the speed bump, the base torque value increases by 5% to 8% and is then used as the target torque value. When the identified obstacle is a pothole, the base torque value is determined based on the depth and area of ​​the pothole. For every 10mm increase in the depth of the pothole, the base torque value increases by 8% to 10% and is then used as the target torque value. The maximum value of the toothed torque should not exceed 15% of the motor's rated torque.

[0091] Based on the determined target torque value, the controller generates a gear engagement torque command corresponding to the target torque through the motor control module, and smoothly outputs it to the drive motor with the help of the filtering module. Applying the gear engagement torque according to the target torque value keeps the drive-side gears in a proper engagement state, thereby suppressing the knocking impact and abnormal noise caused by bumps.

[0092] In one possible implementation, vehicle driving data, historical torque application data, historical bumpy road condition information, and noise information when the vehicle driver passes through bumpy road conditions during a historical time period are acquired. The vehicle driving data, historical torque application data, historical bumpy road condition information, and noise information are used as model training data to train the target model, enabling the trained target model to output a torque correction coefficient. When bumpy road conditions are present in the video footage, the trained target model outputs the current vehicle's torque correction coefficient to correct the target torque value. Finally, a toothed torque is applied to the vehicle's motor based on the corrected target torque value.

[0093] In this embodiment, multimodal data of the driver passing through bumpy areas within a historical time period (e.g., within one month) is collected. This data may include: vehicle driving status, historical torque application data, historical bumpy road condition information, noise information, etc. This data is used as training samples to train a lightweight target model. The trained template model can output a torque correction coefficient based on the current driving status of the vehicle, bumpy road conditions, and target torque value. This coefficient is used to correct the target torque and disengage the generator when the vehicle is in motion based on the identified road and vehicle conditions.

[0094] Specifically, vehicle driving data may include, but is not limited to: vehicle speed, wheel speed, gear position, longitudinal and lateral acceleration, pitch angle change, steering angle, wheel-side torque demand, energy recovery intensity, etc.; historical torque application data may include, but is not limited to: actual issued gear torque application commands (torque value, application time, duration, rate of increase / decrease, etc.); historical bumpy road condition information may include, but is not limited to: road condition type (speed bump / pothole, etc.) and its geometric parameters (height, width, depth, area), relative position (longitudinal and lateral); noise information may include, but is not limited to: noise indicators or vibration energy recorded by in-vehicle microphones or vibration sensors (through comparison values ​​or spectral characteristics within a preset time before and after bumpy road conditions). All data is synchronized by timestamp and organized and stored in the vehicle-side or cloud database in units of events.

[0095] The effectiveness of each training sample is evaluated based on noise information and energy consumption changes. A "desired torque correction target" is constructed or estimated, or the noise reduction / energy consumption ratio is used as the optimization objective, providing supervision information or reference labels for subsequent model training. Key features for modeling are extracted from each sample. Typical features include: average / approach speed, bump type and geometric parameters (height / depth / width / area), peak values ​​of vehicle attitude changes, historical torque application characteristics (most recent N amplitudes and durations), and noise baseline and post-event changes. Categorical features are encoded, and numerical features are normalized or standardized.

[0096] A regression or lightweight prediction model suitable for vehicle deployment is employed, using the aforementioned features as input and torque correction coefficient or performance optimization objective as output, for offline training and validation. During training, multi-objective evaluation (e.g., noise reduction, energy consumption increment, and command smoothness) is used, and cross-validation and generalization tests are performed on the model. After training, the model is validated on the validation set to confirm that it achieves the expected balance between noise suppression and energy consumption control.

[0097] The trained quantization model is deployed to the vehicle controller or domain controller. During runtime, when the video identifies bumpy road conditions and both the location and vehicle speed meet the corresponding trigger conditions, the controller collects the features of the current bumpy event and inputs them into the model. The model outputs a torque correction coefficient. The final applied torque is calculated by combining the original target torque value with the torque value, i.e., the final torque value = original target torque value × torque correction coefficient. If the current driver is detected as a new user (without historical data), the default correction coefficient of 1.0 is used, and the data accumulation mode is started. After continuously collecting 10 sets of valid data from the driver, the model is automatically updated and adaptive correction is enabled. In addition, the feedback data of the current applied effect is monitored in real time. If the abnormal noise decibel value exceeds the preset threshold (45 decibels) or the peak vibration acceleration exceeds the standard, the correction coefficient is automatically fine-tuned (each adjustment range ±2%-5%), and the adjusted parameters and effect data are synchronously updated to the driving habit feature database to realize online iterative optimization of the model.

[0098] Before issuing torque commands, the calculation results must be subject to safety constraints and filtering: the corrected torque value must be ensured not to exceed the allowable values ​​of the motor and transmission components; at the same time, the rate of torque change should be limited by slope and low-pass filtered to avoid jerking or system oscillation caused by sudden changes.

[0099] After each event is executed, the actual applied torque, model output correction coefficients, and the resulting noise / vibration feedback and energy consumption impact are recorded. Data buffered at the vehicle end is periodically uploaded to the cloud for aggregation and analysis; the model is then retrained or its parameters fine-tuned based on the new data.

[0100] In one possible implementation, the estimated time for the vehicle to reach the obstacle is calculated based on the current vehicle speed and the longitudinal distance of the bumpy obstacle. The toothed torque is applied at a preset time (0.3-0.5 seconds) before the estimated time to ensure that the toothed torque has reached the target value when the vehicle reaches the obstacle. After the vehicle passes the obstacle, the vibration acceleration signal of the vehicle body is continuously monitored. When the vibration acceleration is less than a preset threshold (usually set to 0.5g, where g is the acceleration due to gravity) and continues for a preset time (0.2-0.4 seconds), the toothed torque is unloaded to avoid premature unloading and secondary impact.

[0101] During the application or unloading of the toothed torque to the motor, the toothed torque is filtered to avoid shocks caused by sudden torque changes. The filtering process combines Kalman filtering and moving average filtering: first, a torque prediction model is established using Kalman filtering to predict the theoretical value of the toothed torque and correct sensor measurement errors; then, moving average filtering smooths the Kalman-filtered torque signal, eliminating instantaneous torque fluctuations. The filtering window size is dynamically adjusted according to vehicle speed. When the vehicle speed is ≤ a preset value (15km / h), the window size is 5-8 sampling points (a smoother torque transition is needed at low speeds); when the vehicle speed is 15km / h < ≤ 30km / h, the window size is 3-5 sampling points (the filtering time can be appropriately shortened at high speeds to ensure response speed).

[0102] This invention provides a method for controlling vehicle torque. By using video recognition to locate bumps and applying gear torque as they approach, preload is applied before the bump arrives, reducing gear impact peaks and knocking noise. Gear torque is applied only when a real risk is detected and vehicle speed and position meet the requirements, avoiding unnecessary energy consumption caused by continuous preload, reducing long-term motor energy consumption and extending driving range. It avoids the jerking sensation caused by sudden torque changes, reduces in-vehicle vibration and noise, and improves the riding experience. Targeted preload reduces gear surface impact and repeated impacts, helping to slow gear surface fatigue and early wear, extending the lifespan of gears, bearings, and other components, and reducing maintenance costs. A torque correction model trained using historical driving data and noise feedback can automatically adjust the strategy based on driving habits and road conditions, continuously optimizing the control effect over time.

[0103] Figure 2 This is a schematic diagram of the structure of a vehicle torque control device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the device specifically includes:

[0104] The first acquisition module 21 is used to acquire the vehicle speed signal and gear signal of the vehicle during the vehicle's operation.

[0105] The second acquisition module 22 is used to acquire video information of the target area around the vehicle based on the gear signal;

[0106] The identification module 23 is used to identify whether there are bumpy road conditions in the video frame based on the video information;

[0107] The control module 24 is used to apply a toothed torque to the motor of the vehicle when the bumpy road condition exists in the video frame, the bumpy road condition meets a preset position condition, and the vehicle speed signal meets a preset vehicle speed condition.

[0108] In one possible implementation, the second acquisition module is specifically used to control the forward-view camera in front of the vehicle to acquire video information of a first target area on the road in front of the vehicle when the gear signal indicates that the vehicle is currently in a forward gear;

[0109] When the gear position signal indicates that the vehicle is currently in reverse gear, the rear-view camera behind the vehicle is controlled to acquire video information of a second target area on the road behind the vehicle.

[0110] When the gear position signal indicates that the vehicle is currently in neutral or park, the front-view camera and the rear-view camera are put into standby mode.

[0111] In one possible implementation, the adjustment module 25 is configured to adjust the lateral and longitudinal ranges of the first target area according to the vehicle speed when the vehicle is in forward gear, and to adjust the lateral and longitudinal ranges of the second target area according to the vehicle speed when the vehicle is in reverse gear, wherein the lateral and longitudinal ranges are positively correlated with the vehicle speed.

[0112] In one possible implementation, the control module is specifically used to determine whether the longitudinal distance between the bumpy road conditions in the video image and the vehicle's center of gravity is less than a preset distance, and whether the lateral distance between the bumpy road conditions and the vehicle's center of gravity is less than half the width of the vehicle, when the energy recovery intensity of the vehicle is zero and the driver's required wheel-side torque signal value of the vehicle is zero.

[0113] If the longitudinal distance is less than a preset distance and the lateral distance is less than half the width of the vehicle, the bumpy road condition is determined to meet the preset position condition. If the vehicle speed signal indicates that the vehicle speed is less than the preset vehicle speed, the vehicle speed signal is determined to meet the preset vehicle speed condition, and a toothed torque is applied to the motor of the vehicle.

[0114] In one possible implementation, the control module is further configured to unload the toothed torque from the motor of the vehicle when the longitudinal distance is greater than or equal to a preset distance.

[0115] Alternatively, if the lateral distance is greater than or equal to half the width of the vehicle, the motor of the vehicle is unloaded with a toothed torque.

[0116] Alternatively, if the vehicle speed signal indicates that the vehicle speed is greater than or equal to the preset vehicle speed, the motor of the vehicle is unloaded with a gear torque.

[0117] Alternatively, if the bumpy road conditions are not present in the video footage, the motor unloads the gear torque for the vehicle.

[0118] In one possible implementation, the control module is further configured to identify the road condition type of the bumpy road conditions;

[0119] When the road condition type is a speed bump, the target torque value is determined based on the height and / or width of the speed bump, and the target torque value is positively correlated with the height and / or width of the speed bump;

[0120] When the road condition type is a pothole, the target torque value is determined based on the depth and / or area of ​​the pothole, and the target torque value is positively correlated with the depth and / or area of ​​the pothole.

[0121] Apply gear torque to the vehicle's motor according to the target torque value.

[0122] In one possible implementation, the first acquisition module is further configured to acquire vehicle driving data, historical torque application data, historical bumpy road condition information, and noise information when the vehicle driver passes through bumpy road conditions during a historical time period.

[0123] Processing module 26 is used to train the target model by using the vehicle driving data, the historical torque application data, the historical bumpy road condition information and the noise information as model training data, so that the trained target model outputs the torque correction coefficient.

[0124] When the video footage shows the bumpy road conditions, the trained target model outputs the torque correction coefficient of the current vehicle, so as to correct the target torque value according to the torque correction coefficient.

[0125] The control module is also configured to apply a gear torque to the motor of the vehicle according to the corrected target torque value.

[0126] The vehicle torque control device provided in this embodiment can be as follows: Figure 2 The apparatus shown can perform, as Figure 1 All steps of the method for controlling vehicle torque, thereby achieving Figure 1 For details on the technical effects of the vehicle torque control method shown, please refer to [link / reference needed]. Figure 1 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0127] Figure 3 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present invention. Figure 3The vehicle 300 shown includes at least one processor 301, a memory 302, at least one network interface 304, and other user interfaces 303. The various components in the vehicle 300 are coupled together via a bus system 305. It is understood that the bus system 305 is used to implement communication between these components. In addition to a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 3 The general designated all buses as Bus System 305.

[0128] The user interface 303 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0129] It is understood that the memory 302 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 302 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0130] In some implementations, memory 302 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 3021 and application program 3022.

[0131] The operating system 3021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 3022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 3022.

[0132] In this embodiment of the invention, by calling the program or instructions stored in the memory 302, specifically the program or instructions stored in the application program 3022, the processor 301 executes the method steps provided in each method embodiment, including, for example:

[0133] During the vehicle's operation, the vehicle's speed signal and gear signal are acquired.

[0134] Video information of the target area around the vehicle is obtained based on the gear position signal;

[0135] The video information is used to identify whether there are bumpy road conditions in the video footage;

[0136] If the bumpy road conditions are present in the video footage, and the bumpy road conditions meet preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, then a toothed torque is applied to the motor of the vehicle.

[0137] The methods disclosed in the above embodiments of the present invention can be applied to processor 301, or implemented by processor 301. Processor 301 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 301 or by instructions in the form of software. The processor 301 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 302. The processor 301 reads the information in memory 302 and, in conjunction with its hardware, completes the steps of the above method.

[0138] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0139] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0140] The vehicle provided in this embodiment can be as follows: Figure 3 The vehicle shown can perform the following actions: Figure 1 All steps of the method for controlling vehicle torque, thereby achieving Figure 1 For details on the technical effects of the vehicle torque control method shown, please refer to [link / reference needed]. Figure 1 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0141] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; it may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and it may also include combinations of the above types of memory.

[0142] When one or more programs in the storage medium can be executed by one or more processors to implement the vehicle torque control method described above, which is executed on the vehicle equipment side.

[0143] The processor is used to execute a vehicle torque control program stored in the memory to implement the following steps of a vehicle torque control method executed on the vehicle equipment side:

[0144] During the vehicle's operation, the vehicle's speed signal and gear signal are acquired.

[0145] Video information of the target area around the vehicle is obtained based on the gear position signal;

[0146] The video information is used to identify whether there are bumpy road conditions in the video footage;

[0147] If the bumpy road conditions are present in the video footage, and the bumpy road conditions meet preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, then a toothed torque is applied to the motor of the vehicle.

[0148] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0149] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0150] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling vehicle torque, characterized in that, include: During the vehicle's operation, the vehicle's speed signal and gear signal are acquired. Video information of the target area around the vehicle is obtained based on the gear position signal; The video information is used to identify whether there are bumpy road conditions in the video footage; If the bumpy road conditions are present in the video footage, and the bumpy road conditions meet preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, then a toothed torque is applied to the motor of the vehicle. The application of gear torque to the motor of the vehicle includes: Identify the road condition type of the bumpy road conditions; When the road condition type is a speed bump, the target torque value is determined based on the height and / or width of the speed bump, and the target torque value is positively correlated with the height and / or width of the speed bump; When the road condition type is a pothole, the target torque value is determined based on the depth and / or area of ​​the pothole, and the target torque value is positively correlated with the depth and / or area of ​​the pothole. Apply gear torque to the vehicle's motor according to the target torque value; The method further includes: calculating the estimated time for the vehicle to reach the obstacle position based on the current vehicle speed and the longitudinal distance of the bumpy road conditions; applying the toothed torque for a preset time before the estimated time; continuously monitoring the vehicle body vibration acceleration signal after the vehicle passes the obstacle; and unloading the toothed torque when the vibration acceleration is less than a preset threshold and continues for a preset time.

2. The method according to claim 1, characterized in that, Based on the gear position signal, video information of the target area around the vehicle is obtained, including: When the gear position signal indicates that the vehicle is currently in drive, the forward-facing camera in front of the vehicle is controlled to acquire video information of a first target area on the road in front of the vehicle; When the gear position signal indicates that the vehicle is currently in reverse gear, the rear-view camera behind the vehicle is controlled to acquire video information of a second target area on the road behind the vehicle. When the gear position signal indicates that the vehicle is currently in neutral or park, the front-view camera and the rear-view camera are put into standby mode.

3. The method according to claim 2, characterized in that, The method further includes: The lateral and longitudinal ranges of the first target area are adjusted according to the vehicle speed when the vehicle is in forward gear, and the lateral and longitudinal ranges of the second target area are adjusted according to the vehicle speed when the vehicle is in reverse gear, wherein the lateral and longitudinal ranges are positively correlated with the vehicle speed.

4. The method according to claim 1, characterized in that, When the bumpy road condition is present in the video footage, and the bumpy road condition meets preset position conditions, and the vehicle speed signal meets preset vehicle speed conditions, a gear torque is applied to the vehicle's motor, including: When the energy recovery intensity of the vehicle is zero and the driver's required wheel-side torque signal value is zero, determine whether the longitudinal distance between the bumpy road condition in the video and the center of gravity of the vehicle is less than a preset distance, and determine whether the lateral distance between the bumpy road condition and the center of gravity of the vehicle is less than half the width of the vehicle. If the longitudinal distance is less than a preset distance and the lateral distance is less than half the width of the vehicle, the bumpy road condition is determined to meet the preset position condition. If the vehicle speed signal indicates that the vehicle speed is less than the preset vehicle speed, the vehicle speed signal is determined to meet the preset vehicle speed condition, and a toothed torque is applied to the motor of the vehicle.

5. The method according to claim 4, characterized in that, The method further includes: When the longitudinal distance is greater than or equal to a preset distance, the unloading torque of the motor of the vehicle is applied. Alternatively, if the lateral distance is greater than or equal to half the width of the vehicle, the motor of the vehicle is unloaded with a toothed torque. Alternatively, if the vehicle speed signal indicates that the vehicle speed is greater than or equal to the preset vehicle speed, the motor of the vehicle is unloaded with a gear torque. Alternatively, if the bumpy road conditions are not present in the video footage, the motor unloads the gear torque for the vehicle.

6. The method according to claim 1, characterized in that, The method further includes: Acquire vehicle driving data, historical torque application data, historical bumpy road condition information, and noise information when the vehicle driver passes through bumpy road conditions during a historical time period; The vehicle driving data, the historical torque application data, the historical bumpy road condition information, and the noise information are used as model training data to train the target model so that the trained target model outputs a torque correction coefficient. When the video footage shows the bumpy road conditions, the trained target model outputs the torque correction coefficient of the current vehicle, so as to correct the target torque value according to the torque correction coefficient. The vehicle's motor is subjected to a gear torque based on the corrected target torque value.

7. A vehicle torque control device, characterized in that, include: The first acquisition module is used to acquire the vehicle speed signal and gear signal of the vehicle during the vehicle's operation. The second acquisition module is used to acquire video information of the target area around the vehicle based on the gear signal; The identification module is used to identify whether there are bumpy road conditions in the video footage based on the video information; The control module is used to apply a toothed torque to the motor of the vehicle when the bumpy road condition exists in the video frame, the bumpy road condition meets a preset position condition, and the vehicle speed signal meets a preset vehicle speed condition. The control module is also used to identify the road condition type of the bumpy road conditions; When the road condition type is a speed bump, the target torque value is determined based on the height and / or width of the speed bump, and the target torque value is positively correlated with the height and / or width of the speed bump; When the road condition type is a pothole, the target torque value is determined based on the depth and / or area of ​​the pothole, and the target torque value is positively correlated with the depth and / or area of ​​the pothole. Apply gear torque to the vehicle's motor according to the target torque value; The estimated time for the vehicle to reach the obstacle is calculated based on the current vehicle speed and the longitudinal distance of the bumpy road conditions. The toothed torque is applied starting at a preset time before the estimated time. After the vehicle passes the obstacle, the vibration acceleration signal of the vehicle body is continuously monitored. When the vibration acceleration is less than a preset threshold and continues for a preset time, the toothed torque is unloaded.

8. A vehicle, characterized in that, include: A processor and a memory, the processor being configured to execute a vehicle torque control program stored in the memory to implement the vehicle torque control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the vehicle torque control method according to any one of claims 1 to 6.

Images